Keynote: Mixed Mode Surveys: A Way To Reduce Nonresponse and Costs?
Edith D. de Leeuw, Utrecht University
Reducing nonresponse and limiting survey costs are the two most important reasons to employ multiple modes in survey research. Multiple modes of contact and multiple modes of response may be combined into one mixed-mode design to reach these goals. Previous empirical research suggests that mixed-mode designs are a good tool in the battle against nonresponse. In this presentation I will start with an overview of types of mixed-mode designs and summarize which proved to be effective in reducing nonresponse and cost. However, there are also potential drawbacks to using multiple modes for data collection, such as, increased administrative and logistic burden, and potential for mode specific measurement error. From a Total Survey Error perspective one wants the best of all worlds and reduce overall error. I will discuss the major steps (i.e., design, diagnosis, analysis) necessary in high quality mixed mode studies. Attention will be paid to new technological challenges, such as mobile devices in web surveys and recommendations for research needed for overcoming limitations associated with mixed-mode and mixed device studies will be presented.
Special Session: Mixed Mode and Tailored Designs to Reduce Nonresponse and Costs